List your company

Image-Text Retrieval on COCO 1.0 (test)

48.79R@1CoM-PT
28.270833.597938.92544.2521Apr 14, 2026

Evaluation results

MethodLinks
CoM-PTModel Family=ViT Family, Model=ViT-L/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0448.796.6215.244.5214.97
BaselineModel Family=ViT Family, Model=ViT-L/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0448.0325.3343.2516.2835.52
CoM-PTModel Family=ViT Family, Model=ViT-B/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0446.52.828.622.7510.45
BaselineModel Family=ViT Family, Model=ViT-B/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0446.448.7917.927.9419.24
BaselineModel Family=ViT Family, Model=ViT-M/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0444.875.529.136.211.3
CoM-PTModel Family=ViT Family, Model=ViT-M/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0444.832.195.82.67.7
BaselineModel Family=ViT Family, Model=ViT-S/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0443.233.613.615.15.1
CoM-PTModel Family=ViT Family, Model=ViT-S/16, Pre-training Dataset=Merged-15M, Evaluation Protocol=Zero-shot2026.0443.233.613.615.15.1
CoM-PTModel Family=Swin Family, Model=Swin-L, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0441.950.842.730.734.21
CoM-PTModel Family=Swin Family, Model=Swin-B, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0441.060.521.890.583.48
BaselineModel Family=Swin Family, Model=Swin-L, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0440.237.8614.256.7616
CoM-PTModel Family=Swin Family, Model=Swin-S, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0440.060.431.370.682.9
BaselineModel Family=Swin Family, Model=Swin-B, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0439.843.486.393.739.24
BaselineModel Family=Swin Family, Model=Swin-S, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0439.461.972.913.295.51
CoM-PTModel Family=ViT Family, Model=ViT-L/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0439.181.412.941.023.64
BaselineModel Family=Swin Family, Model=Swin-T, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0437.290.940.942.222.22
CoM-PTModel Family=Swin Family, Model=Swin-T, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0437.290.940.942.222.22
BaselineModel Family=ViT Family, Model=ViT-L/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0436.5310.7916.77.5614.95
CoM-PTModel Family=ViT Family, Model=ViT-B/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0435.670.591.530.542.62
BaselineModel Family=ViT Family, Model=ViT-B/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0434.933.755.913.457.39
CoM-PTModel Family=ViT Family, Model=ViT-S/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0434.150.320.940.522.06
BaselineModel Family=ViT Family, Model=ViT-S/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0432.811.542.162.43.94
BaselineModel Family=ViT Family, Model=ViT-T/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0429.060.620.621.541.54
CoM-PTModel Family=ViT Family, Model=ViT-T/16, Pre-training Dataset=CC3M, Evaluation Protocol=Zero-shot2026.0429.060.620.621.541.54